Skip to content

fix binary file check #377

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wants to merge 9 commits into
base: main
Choose a base branch
from
14 changes: 13 additions & 1 deletion src/gitingest/schemas/filesystem.py
Original file line number Diff line number Diff line change
Expand Up @@ -142,7 +142,7 @@ def content(self) -> str: # pylint: disable=too-many-return-statements
if chunk == b"":
return "[Empty file]"

if not _decodes(chunk, "utf-8"):
if is_binary_file(chunk):
return "[Binary file]"

# Find the first encoding that decodes the sample
Expand All @@ -159,3 +159,15 @@ def content(self) -> str: # pylint: disable=too-many-return-statements
return fp.read()
except (OSError, UnicodeDecodeError) as exc:
return f"Error reading file with {good_enc!r}: {exc}"


def is_binary_file(file_contents: bytes | None) -> bool:
"""Check whether a file is binary by reading its first 1024 bytes and looking for non-text characters."""
if not file_contents:
return False # Empty files are not binary

text_characters = bytes(
{7, 8, 9, 10, 12, 13, 27}.union(set(range(0x20, 0x100)) - {0x7F}),
)
# If translate returns any bytes, those are non-text (binary) bytes
return bool(file_contents.translate(None, text_characters))
6 changes: 4 additions & 2 deletions src/gitingest/utils/file_utils.py
Original file line number Diff line number Diff line change
Expand Up @@ -27,9 +27,11 @@ def _get_preferred_encodings() -> list[str]:
platform's default encoding followed by common fallback encodings.

"""
encodings = [locale.getpreferredencoding(), "utf-8", "utf-16", "utf-16le", "utf-8-sig", "latin"]
encodings = [locale.getpreferredencoding(), "utf-8", "utf-16le", "utf-8-sig", "latin"]
if platform.system() == "Windows":
encodings += ["cp1252", "iso-8859-1"]
encodings += ["utf-16be", "cp1252", "iso-8859-1"]
else:
encodings += ["utf-16"]
return list(dict.fromkeys(encodings))


Expand Down
Loading